| { | |
| "architectures": [ | |
| "Qwen3Model" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "quantization_config": { | |
| "modules_to_not_convert": null, | |
| "quant_method": "torchao", | |
| "quant_type": { | |
| "default": { | |
| "_data": { | |
| "set_inductor_config": true, | |
| "weight_dtype": { | |
| "_data": "float8_e4m3fn", | |
| "_type": "torch.dtype" | |
| } | |
| }, | |
| "_type": "Float8WeightOnlyConfig", | |
| "_version": 1 | |
| } | |
| }, | |
| "quant_type_kwargs": {} | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |